psuu0001

Any plans to release the code?

5

Hi, your work is excellent. Do you have any plans to release the code?

我用自己的声音测的speech_model251_e_0_step_625000.model模型的效果不是很好，但是作者提供的在线demo的效果实测的不错。请问是有在基于speech_model251_e_0_step_625000.model继续训练吗？

把训练的输入改成32，100就可以了。改完之后运行一下，再把参数改回来（65，256），发现也可以正常运行。说实话我自己都不知道怎么解决的这个bug

2

> error: > batch_size, l, d = x.size() > ValueError: too many values to unpack (expected 3) > > x is the input image. > > when I tried to...

ValueError: too many values to unpack (expected 3)

1

error: batch_size, l, d = x.size() ValueError: too many values to unpack (expected 3) x is the input image. when I tried to train the model, the error came up....

ctcdecode的安装和使用问题

1

我想运行beamdecode.py，但是这需要安装ctcdecode。很多次安装失败后，我发现把pytorch降级成1.0的版本后，ctcdecode 0.4就安装成功了，但是再运行beamdecode.py的时候，又报错说pytorch的版本不对应。当我把pytorch升级到3.6以上时，ctcdecode又开始报错了。请问有人成功运行过ctcdecode这个包吗？

Could you offer the demo or test data?

7

The whole dataset processed is so huge. Could you please offer a demo or test data image dir?

Cannot open the dropbox

1

Could you please share other links to download the pre-trained model? cause the dropbbox seems to be unconnected.

How to get the phoneme?

2

Hi, bro, very appreciate for your work. The method to load the model can directly get the word. But I want the phoneme. Do you know how to get the...

make succeed but import failed

1